This is a note to let you know that I've just added the patch titled net/mlx5: Cancel delayed recovery work when unloading the driver to the 4.9-stable tree which can be found at: http://www.kernel.org/git/?p=linux/kernel/git/stable/stable-queue.git;a=summary The filename of the patch is: net-mlx5-cancel-delayed-recovery-work-when-unloading-the-driver.patch and it can be found in the queue-4.9 subdirectory. If you, or anyone else, feels it should not be added to the stable tree, please let <stable@xxxxxxxxxxxxxxx> know about it. >From 2a0165a034ac024b60cca49c61e46f4afa2e4d98 Mon Sep 17 00:00:00 2001 From: Mohamad Haj Yahia <mohamad@xxxxxxxxxxxx> Date: Thu, 30 Mar 2017 17:09:00 +0300 Subject: net/mlx5: Cancel delayed recovery work when unloading the driver From: Mohamad Haj Yahia <mohamad@xxxxxxxxxxxx> commit 2a0165a034ac024b60cca49c61e46f4afa2e4d98 upstream. Draining the health workqueue will ignore future health works including the one that report hardware failure and thus we can't enter error state Instead cancel the recovery flow and make sure only recovery flow won't be scheduled. Fixes: 5e44fca50470 ('net/mlx5: Only cancel recovery work when cleaning up device') Signed-off-by: Mohamad Haj Yahia <mohamad@xxxxxxxxxxxx> Signed-off-by: Moshe Shemesh <moshe@xxxxxxxxxxxx> Signed-off-by: Saeed Mahameed <saeedm@xxxxxxxxxxxx> Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx> --- drivers/net/ethernet/mellanox/mlx5/core/health.c | 15 ++++++++++++++- drivers/net/ethernet/mellanox/mlx5/core/main.c | 2 +- include/linux/mlx5/driver.h | 1 + 3 files changed, 16 insertions(+), 2 deletions(-) --- a/drivers/net/ethernet/mellanox/mlx5/core/health.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/health.c @@ -67,6 +67,7 @@ enum { enum { MLX5_DROP_NEW_HEALTH_WORK, + MLX5_DROP_NEW_RECOVERY_WORK, }; static u8 get_nic_state(struct mlx5_core_dev *dev) @@ -193,7 +194,7 @@ static void health_care(struct work_stru mlx5_handle_bad_state(dev); spin_lock(&health->wq_lock); - if (!test_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags)) + if (!test_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags)) schedule_delayed_work(&health->recover_work, recover_delay); else dev_err(&dev->pdev->dev, @@ -328,6 +329,7 @@ void mlx5_start_health_poll(struct mlx5_ init_timer(&health->timer); health->sick = 0; clear_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + clear_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); health->health = &dev->iseg->health; health->health_counter = &dev->iseg->health_counter; @@ -350,11 +352,22 @@ void mlx5_drain_health_wq(struct mlx5_co spin_lock(&health->wq_lock); set_bit(MLX5_DROP_NEW_HEALTH_WORK, &health->flags); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); spin_unlock(&health->wq_lock); cancel_delayed_work_sync(&health->recover_work); cancel_work_sync(&health->work); } +void mlx5_drain_health_recovery(struct mlx5_core_dev *dev) +{ + struct mlx5_core_health *health = &dev->priv.health; + + spin_lock(&health->wq_lock); + set_bit(MLX5_DROP_NEW_RECOVERY_WORK, &health->flags); + spin_unlock(&health->wq_lock); + cancel_delayed_work_sync(&dev->priv.health.recover_work); +} + void mlx5_health_cleanup(struct mlx5_core_dev *dev) { struct mlx5_core_health *health = &dev->priv.health; --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -1169,7 +1169,7 @@ static int mlx5_unload_one(struct mlx5_c int err = 0; if (cleanup) - mlx5_drain_health_wq(dev); + mlx5_drain_health_recovery(dev); mutex_lock(&dev->intf_state_mutex); if (test_bit(MLX5_INTERFACE_STATE_DOWN, &dev->intf_state)) { --- a/include/linux/mlx5/driver.h +++ b/include/linux/mlx5/driver.h @@ -788,6 +788,7 @@ int mlx5_health_init(struct mlx5_core_de void mlx5_start_health_poll(struct mlx5_core_dev *dev); void mlx5_stop_health_poll(struct mlx5_core_dev *dev); void mlx5_drain_health_wq(struct mlx5_core_dev *dev); +void mlx5_drain_health_recovery(struct mlx5_core_dev *dev); int mlx5_buf_alloc_node(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf, int node); int mlx5_buf_alloc(struct mlx5_core_dev *dev, int size, struct mlx5_buf *buf); Patches currently in stable-queue which might be from mohamad@xxxxxxxxxxxx are queue-4.9/net-mlx5-cancel-delayed-recovery-work-when-unloading-the-driver.patch